Unsupervised Image Classification on ImageNet Superclasses (29 classes) WordNet hierarchy (val)
79.7AccuracySelf-Classifier
Evaluation results
| Method | Links | |
|---|---|---|
| Self-ClassifierBackbone=ResNet-502021.03 | 79.7 | |
| SCANBackbone=ResNet-50, Pre-training=ImageNet-pretrained2021.03 | 79.3 | |
| OBoWBackbone=ResNet-50, Evaluation Protocol=k-means classifier2021.03 | 76.5 | |
| MoCoV2Backbone=ResNet-50, Evaluation Protocol=k-means classifier2021.03 | 72.8 | |
| BarlowTBackbone=ResNet-50, Evaluation Protocol=k-means classifier2021.03 | 72.1 | |
| DINOBackbone=ResNet-50, Evaluation Protocol=k-means classifier2021.03 | 71.3 | |
| SwAVBackbone=ResNet-50, Evaluation Protocol=k-means classifier2021.03 | 69.4 | |
| SeLaBackbone=ResNet-50, Pre-training=ImageNet-pretrained2021.03 | 44.9 |